AB persona-spawn
Spawn subagents with personas from a local workspace library or the Emblem persona marketplace. Use when a task needs a different voice, expertise, or operating style; when the user says "use persona X", "spawn as Y", or "have a specific character do this"; when you need shared org context such as a foundation doc injected into every persona spawn; or when offloading a bounded task to a persona-preserving subagent is better than changing the current agent's own identity. Not for trivial tasks, changing your own persona in-place, or bypassing local subagent policy.
As a process B 67/100 · Nearly there — weak spots: result and completion, inputs and preconditions, running it twice
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The skill asks for more than the task needs: broad tool access, credential environment variables, binaries. Every extra permission widens the damage from a mistake or a compromise.
Narrow allowed-tools and the variable list to the minimum; replace binaries with readable sources or scripts.
How to improve
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 1
✓ No critical or high findings
Medium and low: 1
-
medium Broad scope
meta-agent-memory-dumpassets/personas/the-mandalorian/IDENTITY.mdAgent memory / workspace files bundled with the skill (2) — likely a workspace dump with personal data or tokensassets/personas/the-mandalorian/IDENTITY.md, assets/personas/the-mandalorian/SOUL.md
Files scanned: 12. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 67/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 2 mutating operations with no state check
- 70Failures and branches. 4 branches
- 100Tools and files. No external tools needed
- 100Steps. 23 steps
- 100When it triggers. States when to use and when not to
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1127 tokens
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low The response is described with custom markup (7 tags): a typed call is more reliable
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +3Output format is not stated: the model decides each time
- -31 of 5 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +5Description quotes 3 example trigger phrases
- +4Description says when NOT to use the skill
- +3Description length 570: enough signal without eating the budget
- +4Structure: 17 headings
- +3Step-by-step instructions: 23 items
- +4Has examples (10 code blocks)
- +4Reference files are cited in the instructions (2 of 2)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 94.